GITHUB AGENT SKILLS / 技能收录
给你的 AI 助手
装上专业技能
我们从 GitHub 持续收录、审核并分类优质的 Agent Skills,按职业与使用场景整理,复制一行命令即可安装到 Claude Code、Cursor 等智能体。
按职业浏览 Agent Skills
为不同岗位挑选的高频技能
按使用场景浏览 Agent Skills
从你要完成的任务出发
按创作者浏览 Agent Skills
按 GitHub Stars 排序的优秀创作者
Microsoft
@microsoftopenclaw
@openclawAnthropic
@anthropicsOpenAI
@openaiThe Apache Software Foundation
@apacheGitHub
@githubAutoGPT
@Significant-GravitasGarry Tan
@garrytan全部 Skills 482556
diff-blind-test-synth
暂无简介
wds-0-project-setup
Project onboarding - determine project type, complexity, tech stack, and route to correct phase
design-system
Use this skill to generate or audit design systems, check visual consistency, and review PRs that touch styling. Emits/consumes the single `.design/` artifact contract and scores on the canonical DESIGN-EVAL v1 rubric (9 dims, 0-4) — the legacy 10-dim 0-10 visual-audit scale is RETIRED.
wds-0-alignment-signoff
Create alignment around your idea before starting the project
design-studio
ONE entry to the whole design pipeline over a running app (Reframe, momentstudio, WebCoder, bilbo) — the mode-routed successor to design-review-loop. Runs the full TCR design-review loop (8 gates, G0 PRIME to G7 VERIFY, revert-gate) plus a thin mode router to jump to one stage — direct (scope, define good, pick a direction, palette/font), audit (a11y/contrast/dead-button UI audit, visual review), mirror (code-to-canvas transpose to Figma), critique (design-critique persona panel), iterate (Figma branch, design tokens), implement (Figma-to-code), verify (re-audit delta), loop (the whole pass), drive (drive/point/interact the live app, to ui-drive), session (interactive restyle of a live element, to design-studio-session). Absorbs the folded design skills' triggers — design review, design system audit, frontend design direction, visual review, mirror to Figma, implement design, drive the app, interactive tweak. NOT for a design DOCUMENT (metaswarm review-design) nor rubric math (ui-audit, critique-panel).
bmad-workflow-builder
Builds workflows and skills through conversational discovery and validates existing ones. Use when the user requests to "build a workflow", "modify a workflow", "quality check workflow", or "optimize skill".
design-studio-session
The interactive-modify capability behind `design-studio session` mode. Use when the owner wants to point at a LIVE element in a running app (Reframe, momentstudio, WebCoder, bilbo) and iteratively restyle it with Claude and Codex — preview candidates as injected style overlays FIRST, resolve the clicked element back to its source file:line, apply ONE scoped micro-commit, incrementally re-audit only the changed screen, and auto-decide KEEP or REVERT through the SAME revert-gate as the batch design-review loop. Do NOT use for a whole-app batch audit (use design-review-loop / ui-audit) or for driving the app without modifying it (use ui-drive).
bmad-validate-prd
Validate a PRD against standards. Use when the user says "validate this PRD" or "run PRD validation"
design-review-loop
MOVED — renamed to design-studio. This is a redirect tombstone kept so in-flight invocations of the old name still resolve. Use the design-studio skill instead; it is the SAME TCR design-review loop (G0 PRIME to G7 VERIFY, revert-gate) plus a thin mode router. Pick a mode — direct, audit, mirror, critique, iterate, implement, verify, loop, drive, session — or run design-studio loop for the whole pass. Triggers that used to land here (design review, run the design-review loop, TCR loop, audit the UI, transpose or mirror to Figma, design critique, implement the design, iterate design, drive the app, interactive design tweak) now route through design-studio.
deep-research
Multi-source research with runtime MCP tool inventory, live/down/quota preflight, role-scoped routing, caching, academic consolidation, FACT/RACE-style verification, two-axis source assessment, and grounded cited reports. Use for thorough evidence-backed research, due diligence, technology evaluation, or current-state synthesis.
bmad-testarch-trace
Generate traceability matrix and quality gate decision. Use when the user says "lets create traceability matrix" or "I want to analyze test coverage"
cv-studio
暂无简介
bmad-testarch-test-review
Review test quality using best practices validation. Use when user says "lets review tests" or "I want to evaluate test quality"
council
Convene a four-voice council for ambiguous decisions, tradeoffs, and go/no-go calls. Use when multiple valid paths exist and you need structured disagreement before choosing.
bmad-testarch-test-design
Create system-level or epic-level test plans. Use when the user says "lets design test plan" or "I want to create test strategy"
compchem-validators
Use when a docking / MD / free-energy campaign needs an OUTPUT quality gate - post-dock pose validity (PoseBusters), a cheap-tier prefilter before the token-gated tiers (Uni-Dock GPU-Vina before Glide, Boltz-2 affinity before FEP+/QDX credits), or a "docking done / ΔG=… / MD converged" claim that should be backed by a validity artifact before it is treated as done. compchem-preflight guards INPUT; this skill guards OUTPUT (a pose can score well yet be physically impossible). Also the map for the open-weights compute arm - MACE-OFF near-DFT MD, OpenFE token-free FEP twin, REINVENT 4 generative loop, PLINDER leakage-free splits, and the TxAgent/ToolUniverse grounded-reasoning pattern (Opus reasoner, not the fine-tuned model). All ride the existing schrodinger / qdx-rush / cloud-hub MCPs - scientific compute is NOT agent runtime. Do NOT use for the receptor-prep-to-dock pipeline itself (use structure-based-screening) or license-free cheminformatics (use cheminformatics-rdkit).
bmad-testarch-nfr
Assess NFRs like performance security and reliability. Use when the user says "lets assess NFRs" or "I want to evaluate non-functional requirements"
codex-databricks-fanout
Use when fanning out Codex CLI agents onto Databricks — running many parallel Codex/LLM work units on job clusters, scaling past a local RAM ceiling, or deciding between Databricks / local / Modal / RunPod for a large agent fan-out. Carries the measured constraints from a 608-unit production run + a 48-unit auth-research re-prove so a session does not re-derive them wrong.